INDEX

Explanations

the term "underlying" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÄįÃŃ

-0.15

anne

-0.15

çĩ

-0.15

 MetroFramework

-0.15

*__

-0.15

ASURE

-0.15

shaft

-0.15

mana

-0.15

iras

-0.15

ìĭľìĺ¤

-0.15

POSITIVE LOGITS

Lex

0.16

 underlying

0.15

 ÑģÐ¾Ð±Ð¾Ð¹

0.15

gence

0.14

 extremes

0.14

ubu

0.14

ÙĦØ³

0.14

attice

0.14

 commitment

0.14

onnement

0.14

Activations Density 0.006%

the term "underlying" in various contexts

No Comments

No Known Activations